{"id":"W3202137189","doi":"10.48550/arxiv.2109.13066","title":"Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questions","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; SQL; Prefix; Task (project management); Data definition language; Benchmark (surveying); Construct (python library); SQL injection; Stored procedure; Metric (unit); SQL/PSM; Programming language; Database; Query by Example; Information retrieval","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002766273,0.00243085,0.001006202,0.001661342,0.0005066656,0.001737093,0.002744318,0.002335366,0.01497306],"category_scores_gemma":[0.01793181,0.0005588988,0.001351676,0.001059612,0.0006883027,0.004255524,0.003091836,0.001951676,0.007855507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008168681,"about_ca_system_score_gemma":0.001956169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003367502,"about_ca_topic_score_gemma":0.004866112,"domain_scores_codex":[0.9970403,0.001171374,0.0002821948,0.0008054112,0.0005400176,0.0001607515],"domain_scores_gemma":[0.9886148,0.007191807,0.0004301264,0.002144841,0.001174265,0.0004441724],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002237281,0.001356586,0.01782542,0.002759002,0.0003086639,0.001070768,0.00172053,0.04976283,0.03196396,0.01189991,0.2114095,0.6676854],"study_design_scores_gemma":[0.0003170425,0.0006664914,0.003758109,0.000141908,0.00008949889,0.0007996464,0.0007517404,0.8665354,0.04888486,0.02211917,0.05583232,0.0001037206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1437645,0.001589449,0.5748853,0.001785943,0.0006851755,0.001927003,0.03084383,0.2334489,0.01106985],"genre_scores_gemma":[0.3962459,0.0004411551,0.4963261,0.001145381,0.0002093455,0.001522478,0.09047975,0.004656579,0.008973342],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01497306,"threshold_uncertainty_score":0.05008984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1141670447659727,"score_gpt":0.2023945811433634,"score_spread":0.08822753637739075,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}